Name: crabbox
Rating: 57.599999999999994 (1 reviews)
Author: openclaw

crabbox

Use the Crabbox wrapper for OpenClaw remote validation across Linux, macOS, Windows, and WSL2, including delegated Blacksmith Testbox proof. Report the actual provider and id.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/crabbox/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable, packed with executable commands and clear validation-gated workflows with feedback loops, but the ~700-line monolithic body repeats env-var boilerplate and inlines reference catalogs instead of splitting them into bundle files. Progressive disclosure and conciseness are the weakest dimensions.

Suggestions

Extract the Observability Flags catalog and the desktop/WebVNC + diagnostics command listings into reference files (e.g. references/flags.md, references/desktop.md) and link to them from the body, reducing the main SKILL.md to an overview.

Dedupe the repeated CI env-var prefix ('CI=1 NODE_OPTIONS=... OPENCLAW_TEST_PROJECTS_PARALLEL=6 ...') by defining it once as a variable or snippet and referencing it, instead of repeating it verbatim in every example.

Consolidate the duplicated Blacksmith footgun and cleanup notes (currently restated in 'If Crabbox Fails', 'Blacksmith Backend Notes', and 'Failure Triage') into a single shared section to remove redundancy.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence with no basic-concept padding, but the long CI env-var prefix is repeated verbatim across 4+ command examples and Blacksmith footgun/cleanup notes are duplicated across sections, so it is mostly efficient but could be tightened (anchor 2) rather than lean with every token earning its place (anchor 3).	2 / 3
Actionability	It provides extensive fully-executable shell commands with concrete flags and copy-paste-ready examples (warmup/run/stop, desktop/webvnc, diagnostics, E2E templates), matching the anchor 3 example of specific, executable guidance.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced (the numbered E2E verification flow) with explicit validation checkpoints ('Verify cleanup when a run fails', 'prove the expected command before handing off', 'Read the JSON summary... exitCode') and feedback loops in the 'If Crabbox Fails' triage, matching anchor 3.	3 / 3
Progressive Disclosure	The body is well-sectioned with clear headers, but it is a ~700-line monolith with no bundle files and inlines reference material (the Observability Flags catalog, desktop/WebVNC and diagnostics command listings) that could be split out, matching anchor 2 ('content that should be separate is inline') rather than the split, one-level-deep references of anchor 3.	2 / 3
	Total	10 / 12 Passed

Description

57%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description carves out a clear, distinctive niche with concrete platform coverage, but it leans on domain jargon and omits an explicit 'Use when...' trigger clause, capping completeness and trigger-term quality at 2. Specificity is solid but its core verbs ('validation', 'proof') stay somewhat abstract.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g. 'Use when the user asks to run OpenClaw tests remotely, test in Crabbox, or needs Blacksmith Testbox proof').

Lead the capability statement with a concrete third-person verb and list specific actions (e.g. 'Runs, warms up, and stops remote Crabbox leases; dispatches broad pnpm gates; inspects logs and artifacts') instead of the abstract 'remote validation'.

Include common natural-language variations users would actually say ('test in Crabbox', 'run tests on Testbox', 'remote CI proof') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('OpenClaw remote validation') across concrete platforms plus 'delegated Blacksmith Testbox proof' and 'Report the actual provider and id', but the core actions ('validation', 'proof') are abstract rather than a comprehensive list of concrete actions, so it sits at anchor 2 and not 3.	2 / 3
Completeness	It clearly states what the skill does but the 'when' is only implied (no explicit 'Use when...' clause), so per the guideline completeness is capped at 2 rather than reaching the explicit-trigger anchor 3.	2 / 3
Trigger Term Quality	Relevant keywords are present ('Crabbox wrapper', 'Blacksmith Testbox', 'Linux, macOS, Windows, and WSL2') but they are domain jargon with no natural 'Use when...' trigger phrasing or common variations, matching anchor 2 rather than the full natural-term coverage of anchor 3.	2 / 3
Distinctiveness Conflict Risk	The unique 'Crabbox wrapper' / 'OpenClaw' / 'Blacksmith Testbox' niche is highly specific with distinct identifiers, making it unlikely to trigger for the wrong skill, matching the anchor 3 example.	3 / 3
	Total	9 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (712 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	14 / 16 Passed

Repository: openclaw/acpx
Path: .agents/skills/crabbox/SKILL.md
Commit: 504040f

Reviewed: about 20 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.